Merge branch 'linus' into locking/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

12 files changed, 103 insertions, 54 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 045646da97cc..6c772adabad2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1289,7 +1289,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	info_len = min_t(u32, sizeof(info), info_len);
 
 	if (copy_from_user(&info, uinfo, info_len))
-		return err;
+		return -EFAULT;
 
 	info.type = prog->type;
 	info.id = prog->aux->id;
@@ -1312,7 +1312,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
 	}
 
 	ulen = info.xlated_prog_len;
-	info.xlated_prog_len = bpf_prog_size(prog->len);
+	info.xlated_prog_len = bpf_prog_insn_size(prog);
 	if (info.xlated_prog_len && ulen) {
 		uinsns = u64_to_user_ptr(info.xlated_prog_insns);
 		ulen = min_t(u32, info.xlated_prog_len, ulen);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index af9e84a4944e..664d93972373 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1865,10 +1865,12 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 	 * do our normal operations to the register, we need to set the values
 	 * to the min/max since they are undefined.
 	 */
-	if (min_val == BPF_REGISTER_MIN_RANGE)
-		dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
-	if (max_val == BPF_REGISTER_MAX_RANGE)
-		dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	if (opcode != BPF_SUB) {
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+	}
 
 	switch (opcode) {
 	case BPF_ADD:
@@ -1879,10 +1881,17 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env,
 		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_SUB:
+		/* If one of our values was at the end of our ranges, then the
+		 * _opposite_ value in the dst_reg goes to the end of our range.
+		 */
+		if (min_val == BPF_REGISTER_MIN_RANGE)
+			dst_reg->max_value = BPF_REGISTER_MAX_RANGE;
+		if (max_val == BPF_REGISTER_MAX_RANGE)
+			dst_reg->min_value = BPF_REGISTER_MIN_RANGE;
 		if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE)
-			dst_reg->min_value -= min_val;
+			dst_reg->min_value -= max_val;
 		if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE)
-			dst_reg->max_value -= max_val;
+			dst_reg->max_value -= min_val;
 		dst_reg->min_align = min(src_align, dst_align);
 		break;
 	case BPF_MUL:
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 793565c05742..8b4c3c2f2509 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -33,6 +33,9 @@ struct cgroup_taskset {
 	struct list_head	src_csets;
 	struct list_head	dst_csets;
 
+	/* the number of tasks in the set */
+	int			nr_tasks;
+
 	/* the subsys currently being processed */
 	int			ssid;
 
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 620794a20a33..df2e0f14a95d 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2006,6 +2006,8 @@ static void cgroup_migrate_add_task(struct task_struct *task,
 	if (!cset->mg_src_cgrp)
 		return;
 
+	mgctx->tset.nr_tasks++;
+
 	list_move_tail(&task->cg_list, &cset->mg_tasks);
 	if (list_empty(&cset->mg_node))
 		list_add_tail(&cset->mg_node,
@@ -2094,21 +2096,19 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 	struct css_set *cset, *tmp_cset;
 	int ssid, failed_ssid, ret;
 
-	/* methods shouldn't be called if no task is actually migrating */
-	if (list_empty(&tset->src_csets))
-		return 0;
-
 	/* check that we can legitimately attach to the cgroup */
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ss->can_attach) {
-			tset->ssid = ssid;
-			ret = ss->can_attach(tset);
-			if (ret) {
-				failed_ssid = ssid;
-				goto out_cancel_attach;
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ss->can_attach) {
+				tset->ssid = ssid;
+				ret = ss->can_attach(tset);
+				if (ret) {
+					failed_ssid = ssid;
+					goto out_cancel_attach;
+				}
 			}
-		}
-	} while_each_subsys_mask();
+		} while_each_subsys_mask();
+	}
 
 	/*
 	 * Now that we're guaranteed success, proceed to move all tasks to
@@ -2137,25 +2137,29 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx)
 	 */
 	tset->csets = &tset->dst_csets;
 
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ss->attach) {
-			tset->ssid = ssid;
-			ss->attach(tset);
-		}
-	} while_each_subsys_mask();
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ss->attach) {
+				tset->ssid = ssid;
+				ss->attach(tset);
+			}
+		} while_each_subsys_mask();
+	}
 
 	ret = 0;
 	goto out_release_tset;
 
 out_cancel_attach:
-	do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
-		if (ssid == failed_ssid)
-			break;
-		if (ss->cancel_attach) {
-			tset->ssid = ssid;
-			ss->cancel_attach(tset);
-		}
-	} while_each_subsys_mask();
+	if (tset->nr_tasks) {
+		do_each_subsys_mask(ss, ssid, mgctx->ss_mask) {
+			if (ssid == failed_ssid)
+				break;
+			if (ss->cancel_attach) {
+				tset->ssid = ssid;
+				ss->cancel_attach(tset);
+			}
+		} while_each_subsys_mask();
+	}
 out_release_tset:
 	spin_lock_irq(&css_set_lock);
 	list_splice_init(&tset->dst_csets, &tset->src_csets);
@@ -2997,11 +3001,11 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	cgrp->subtree_control &= ~disable;
 
 	ret = cgroup_apply_control(cgrp);
-
 	cgroup_finalize_control(cgrp, ret);
+	if (ret)
+		goto out_unlock;
 
 	kernfs_activate(cgrp->kn);
-	ret = 0;
 out_unlock:
 	cgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
@@ -4669,6 +4673,10 @@ int __init cgroup_init(void)
 
 		if (ss->bind)
 			ss->bind(init_css_set.subsys[ssid]);
+
+		mutex_lock(&cgroup_mutex);
+		css_populate_dir(init_css_set.subsys[ssid]);
+		mutex_unlock(&cgroup_mutex);
 	}
 
 	/* init_css_set.subsys[] has been updated, re-hash */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index ca8376e5008c..8d5151688504 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -63,6 +63,7 @@
 #include <linux/cgroup.h>
 #include <linux/wait.h>
 
+DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
 
 /* See "Frequency meter" comments, below. */
diff --git a/kernel/futex.c b/kernel/futex.c
index ad0af4df1b9d..0939255fc750 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -670,13 +670,14 @@ again:
 		 * this reference was taken by ihold under the page lock
 		 * pinning the inode in place so i_lock was unnecessary. The
 		 * only way for this check to fail is if the inode was
-		 * truncated in parallel so warn for now if this happens.
+		 * truncated in parallel which is almost certainly an
+		 * application bug. In such a case, just retry.
 		 *
 		 * We are not calling into get_futex_key_refs() in file-backed
 		 * cases, therefore a successful atomic_inc return below will
 		 * guarantee that get_futex_key() will still imply smp_mb(); (B).
 		 */
-		if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) {
+		if (!atomic_inc_not_zero(&inode->i_count)) {
 			rcu_read_unlock();
 			put_page(page);
 
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index aee8f7ec40af..638eb9c83d9f 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -95,8 +95,13 @@ static bool migrate_one_irq(struct irq_desc *desc)
 		affinity = cpu_online_mask;
 		brokeaff = true;
 	}
-
-	err = irq_do_set_affinity(d, affinity, true);
+	/*
+	 * Do not set the force argument of irq_do_set_affinity() as this
+	 * disables the masking of offline CPUs from the supplied affinity
+	 * mask and therefore might keep/reassign the irq to the outgoing
+	 * CPU.
+	 */
+	err = irq_do_set_affinity(d, affinity, false);
 	if (err) {
 		pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n",
 				    d->irq, err);
diff --git a/kernel/pid.c b/kernel/pid.c
index 731c4e528f4e..c69c30d827e5 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -575,13 +575,10 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
  */
 void __init pidhash_init(void)
 {
-	unsigned int pidhash_size;
-
 	pid_hash = alloc_large_system_hash("PID", sizeof(*pid_hash), 0, 18,
 					   HASH_EARLY | HASH_SMALL | HASH_ZERO,
 					   &pidhash_shift, NULL,
 					   0, 4096);
-	pidhash_size = 1U << pidhash_shift;
 }
 
 void __init pidmap_init(void)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 17c667b427b4..0869b20fba81 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2069,7 +2069,7 @@ out:
 /**
  * try_to_wake_up_local - try to wake up a local task with rq lock held
  * @p: the thread to be awakened
- * @cookie: context's cookie for pinning
+ * @rf: request-queue flags for pinning
  *
  * Put @p on the run-queue if it's not already there. The caller must
  * ensure that this_rq() is locked, @p is bound to this_rq() and not
diff --git a/kernel/signal.c b/kernel/signal.c
index caed9133ae52..7e33f8c583e6 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3303,12 +3303,15 @@ SYSCALL_DEFINE1(sigpending, old_sigset_t __user *, set)
 #ifdef CONFIG_COMPAT
 COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set32)
 {
+#ifdef __BIG_ENDIAN
 	sigset_t set;
-	int err = do_sigpending(&set, sizeof(old_sigset_t)); 
-	if (err == 0)
-		if (copy_to_user(set32, &set, sizeof(old_sigset_t)))
-			err = -EFAULT;
+	int err = do_sigpending(&set, sizeof(set.sig[0]));
+	if (!err)
+		err = put_user(set.sig[0], set32);
 	return err;
+#else
+	return sys_rt_sigpending((sigset_t __user *)set32, sizeof(*set32));
+#endif
 }
 #endif
 
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 71ce3f4eead3..8f5d1bf18854 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1495,7 +1495,7 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem)
 		base->is_idle = false;
 	} else {
 		if (!is_max_delta)
-			expires = basem + (nextevt - basej) * TICK_NSEC;
+			expires = basem + (u64)(nextevt - basej) * TICK_NSEC;
 		/*
 		 * If we expect to sleep more than a tick, mark the base idle:
 		 */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index a86688fabc55..ca937b0c3a96 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3577,6 +3577,13 @@ static bool wq_calc_node_cpumask(const struct workqueue_attrs *attrs, int node,
 
 	/* yeap, return possible CPUs in @node that @attrs wants */
 	cpumask_and(cpumask, attrs->cpumask, wq_numa_possible_cpumask[node]);
+
+	if (cpumask_empty(cpumask)) {
+		pr_warn_once("WARNING: workqueue cpumask: online intersect > "
+				"possible intersect\n");
+		return false;
+	}
+
 	return !cpumask_equal(cpumask, attrs->cpumask);
 
 use_dfl:
@@ -3744,8 +3751,12 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq,
 		return -EINVAL;
 
 	/* creating multiple pwqs breaks ordering guarantee */
-	if (WARN_ON((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)))
-		return -EINVAL;
+	if (!list_empty(&wq->pwqs)) {
+		if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
+			return -EINVAL;
+
+		wq->flags &= ~__WQ_ORDERED;
+	}
 
 	ctx = apply_wqattrs_prepare(wq, attrs);
 	if (!ctx)
@@ -3929,6 +3940,16 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 	struct workqueue_struct *wq;
 	struct pool_workqueue *pwq;
 
+	/*
+	 * Unbound && max_active == 1 used to imply ordered, which is no
+	 * longer the case on NUMA machines due to per-node pools.  While
+	 * alloc_ordered_workqueue() is the right way to create an ordered
+	 * workqueue, keep the previous behavior to avoid subtle breakages
+	 * on NUMA.
+	 */
+	if ((flags & WQ_UNBOUND) && max_active == 1)
+		flags |= __WQ_ORDERED;
+
 	/* see the comment above the definition of WQ_POWER_EFFICIENT */
 	if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient)
 		flags |= WQ_UNBOUND;
@@ -4119,13 +4140,14 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 	struct pool_workqueue *pwq;
 
 	/* disallow meddling with max_active for ordered workqueues */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return;
 
 	max_active = wq_clamp_max_active(max_active, wq->flags, wq->name);
 
 	mutex_lock(&wq->mutex);
 
+	wq->flags &= ~__WQ_ORDERED;
 	wq->saved_max_active = max_active;
 
 	for_each_pwq(pwq, wq)
@@ -5253,7 +5275,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 	 * attributes breaks ordering guarantee.  Disallow exposing ordered
 	 * workqueues.
 	 */
-	if (WARN_ON(wq->flags & __WQ_ORDERED))
+	if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT))
 		return -EINVAL;
 
 	wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL);